{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.9083620309829712, "min": 1.8701623678207397, "max": 3.295753002166748, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 40487.80859375, "min": 21909.728515625, "max": 116174.859375, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 60.3780487804878, "min": 42.60344827586207, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19804.0, "min": 7900.0, "max": 26356.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1549.2479446948657, "min": 1201.1731570362992, "max": 1554.2867745415815, "count": 492 }, "SoccerTwos.Self-play.ELO.sum": { "value": 254076.66292995797, "min": 2403.92563261748, "max": 342515.3310216315, "count": 492 }, "SoccerTwos.Step.mean": { "value": 4999864.0, "min": 9932.0, "max": 4999864.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999864.0, "min": 9932.0, "max": 4999864.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.0015505763003602624, "min": -0.08583631366491318, "max": 0.15597806870937347, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 0.2542945146560669, "min": -15.364700317382812, "max": 27.501192092895508, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0058425962924957275, "min": -0.08904243260622025, "max": 0.1600945144891739, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.9581857919692993, "min": -15.93859577178955, "max": 28.160961151123047, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.1581341457076189, "min": -0.6634909110990438, "max": 0.39891763645059924, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 25.9339998960495, "min": -50.5407999753952, "max": 56.88680016994476, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.1581341457076189, "min": -0.6634909110990438, "max": 0.39891763645059924, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 25.9339998960495, "min": -50.5407999753952, "max": 56.88680016994476, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01381340757458626, "min": 0.01106493189615018, "max": 0.024011059190767507, "count": 240 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01381340757458626, "min": 0.01106493189615018, "max": 0.024011059190767507, "count": 240 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.11282804906368256, "min": 4.252453345543472e-05, "max": 0.12220808764298757, "count": 240 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.11282804906368256, "min": 4.252453345543472e-05, "max": 0.12220808764298757, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.11486122111479441, "min": 4.2571803108633805e-05, "max": 0.12413785929481189, "count": 240 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.11486122111479441, "min": 4.2571803108633805e-05, "max": 0.12413785929481189, "count": 240 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 240 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 240 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 240 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1706252404", "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul 5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]", "command_line_arguments": "\\\\?\\C:\\Users\\elsa917\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./soccerTwo.yaml --env=./SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cpu", "numpy_version": "1.23.5", "end_time_seconds": "1706264835" }, "total": 12431.145774600001, "count": 1, "self": 0.335086200002479, "children": { "run_training.setup": { "total": 0.11811050000005707, "count": 1, "self": 0.11811050000005707 }, "TrainerController.start_learning": { "total": 12430.6925779, "count": 1, "self": 8.306792599501932, "children": { "TrainerController._reset_env": { "total": 4.888159100000848, "count": 25, "self": 4.888159100000848 }, "TrainerController.advance": { "total": 12417.367653400499, "count": 340498, "self": 8.01775750059278, "children": { "env_step": { "total": 5968.070108200105, "count": 340498, "self": 4631.6375530994155, "children": { "SubprocessEnvManager._take_step": { "total": 1331.0929218002866, "count": 340498, "self": 42.983509300459446, "children": { "TorchPolicy.evaluate": { "total": 1288.1094124998272, "count": 631324, "self": 1288.1094124998272 } } }, "workers": { "total": 5.33963330040342, "count": 340498, "self": 0.0, "children": { "worker_root": { "total": 12416.357360500515, "count": 340498, "is_parallel": true, "self": 8743.221733501156, "children": { "steps_from_proto": { "total": 0.04094869999926232, "count": 50, "is_parallel": true, "self": 0.00824190000184899, "children": { "_process_rank_one_or_two_observation": { "total": 0.03270679999741333, "count": 200, "is_parallel": true, "self": 0.03270679999741333 } } }, "UnityEnvironment.step": { "total": 3673.094678299359, "count": 340498, "is_parallel": true, "self": 176.58975499843245, "children": { "UnityEnvironment._generate_step_input": { "total": 142.32844469985866, "count": 340498, "is_parallel": true, "self": 142.32844469985866 }, "communicator.exchange": { "total": 2783.00880460009, "count": 340498, "is_parallel": true, "self": 2783.00880460009 }, "steps_from_proto": { "total": 571.167674000978, "count": 680996, "is_parallel": true, "self": 116.51077979990987, "children": { "_process_rank_one_or_two_observation": { "total": 454.6568942010681, "count": 2723984, "is_parallel": true, "self": 454.6568942010681 } } } } } } } } } } }, "trainer_advance": { "total": 6441.279787699801, "count": 340498, "self": 56.869217100065725, "children": { "process_trajectory": { "total": 1303.297275299747, "count": 340498, "self": 1301.9161581997482, "children": { "RLTrainer._checkpoint": { "total": 1.3811170999988462, "count": 10, "self": 1.3811170999988462 } } }, "_update_policy": { "total": 5081.113295299989, "count": 240, "self": 664.5548821000411, "children": { "TorchPOCAOptimizer.update": { "total": 4416.558413199948, "count": 7206, "self": 4416.558413199948 } } } } } } }, "trainer_threads": { "total": 1.0999992809956893e-06, "count": 1, "self": 1.0999992809956893e-06 }, "TrainerController._save_models": { "total": 0.12997169999835023, "count": 1, "self": 0.006059199999072007, "children": { "RLTrainer._checkpoint": { "total": 0.12391249999927823, "count": 1, "self": 0.12391249999927823 } } } } } } }